【754】机器学习、多分类、情感分析

多分类问题

• 参考：3 种方法实现逻辑回归多分类【OneVsOne, OneVsRest】
• 参考：《少年的你》短评情感分析——机器学习之逻辑回归
• 参考：sklearn.multiclass.OneVsOneClassifier【中文版】、【英文版】
• 参考：Python机器学习-多元分类的5种模型

逻辑回归

• 参考：机器学习笔记（四）：逻辑回归的多分类

SVM

• 参考：如何使用sklearn中的SVM【SVC分类、SVR回归】
• 参考：Scikit-learn实战之SVM分类

决策树

• 参考：决策树实现鸢尾花三分类

随机森林

• 参考：随机森林分类器（Random Forest）

AdaBoost

• 参考：sklearn机器学习：AdaBoost分类器
• 参考：scikit-learn Adaboost类库使用小结

朴素贝叶斯

• 参考：朴素贝叶斯的三个常用模型：高斯(GaussianNB)、多项式(multinomial model)、伯努利(Bernoulli model)

KNN

• 参考：监督学习算法1: K-近邻(KNN)
• 参考：KNN之iris鸢尾花数据集的分类

GradientBoosting

• 参考：一文读懂机器学习分类算法（附图文详解）
• 参考：Python机器学习库笔记（6）——scikit-learn：分类模型

参考：机器学习：sklearn中xgboost模块的XGBClassifier函数(分类)

---

将多分类转换为二分类来进行相应的计算

相关代码：

1. LogisticRegression

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.multiclass import OneVsRestClassifier
from sklearn.multiclass import OneVsOneClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

data_iris = datasets.load_iris()
x, y = data_iris.data, data_iris.target
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3,random_state = 0)

# 使用multiclass的OvO多分类策略,分类器使用LogisticRegression
model = OneVsOneClassifier(LogisticRegression(C=1.0, tol=1e-6))
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))
============================================
0.9555555555555556

# 使用multiclass的OvR多分类策略,分类器使用LogisticRegression
model = OneVsRestClassifier(LogisticRegression(C=1.0, tol=1e-6))
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))
============================================
0.8888888888888888

2. SVM

SVC

from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.multiclass import OneVsRestClassifier
from sklearn.multiclass import OneVsOneClassifier
from sklearn import svm
from sklearn.metrics import accuracy_score

data_iris = datasets.load_iris()
x, y = data_iris.data, data_iris.target
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size = 0.3,random_state = 0)

# 使用multiclass的OvO多分类策略,分类器使用SVM
model = OneVsOneClassifier(svm.SVC())
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))
============================================
0.9555555555555556

# 使用multiclass的OvR多分类策略,分类器使用SVM
model = OneVsRestClassifier(svm.SVC())
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))
============================================
0.8888888888888888

LinearSVC

# 使用multiclass的OvR多分类策略,分类器使用SVM
model = OneVsRestClassifier(svm.LinearSVC())
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))

3. Decision Tree

from sklearn.tree import DecisionTreeClassifier

model = DecisionTreeClassifier()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

4. Random Forest

from sklearn.ensemble import RandomForestClassifier

model = RandomForestClassifier(n_jobs=2)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

5. AdaBoost

from sklearn.ensemble import AdaBoostClassifier

model = AdaBoostClassifier(DecisionTreeClassifier(),
                           algorithm="SAMME",
                           n_estimators=200, 
                           learning_rate=0.5)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

6. 朴素贝叶斯

MultinomialNB

from sklearn.naive_bayes import MultinomialNB, GaussianNB

model = MultinomialNB(alpha=1.0, class_prior=None, fit_prior=True)
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

GaussianNB

model = GaussianNB()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

BernoulliNB

model = BernoulliNB()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

7. KNN

from sklearn.neighbors import KNeighborsClassifier 

model = KNeighborsClassifier()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

8. GradientBoosting

from sklearn.ensemble import GradientBoostingClassifier

model = GradientBoostingClassifier()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred)) 

9. XGBoost

from xgboost.sklearn import XGBClassifier

model = XGBClassifier()
model.fit(x_train, y_train)
y_pred = model.predict(x_test)
print(accuracy_score(y_test, y_pred))